Pandas util functions

pandas_utils.py

import pandas as pd

def clean_str_cols(df, encoding='ascii'):
    """
    As string columns are stored as 'objects' it can cause many problems, especially when reading and writig CSVs. This function
    forces the columns to be strings and be encoded as a specified encoding.
    
    Solves `UnicodeEncodeError` errors when using `to_csv`.
    """
    df = df.copy()

    for col, dtype in df.dtypes.items():
        if dtype.kind == 'O':   # If string datatype
            df[col] = df[col].astype('str')  # The col can be reported as being a object when it contains mixed datatypes
            df[col] = df[col].str.encode(encoding, errors='ignore').str.decode(encoding)

    return df